aboutsummaryrefslogtreecommitdiffstats
path: root/net/openvswitch
diff options
context:
space:
mode:
Diffstat (limited to 'net/openvswitch')
-rw-r--r--net/openvswitch/actions.c60
-rw-r--r--net/openvswitch/conntrack.c139
-rw-r--r--net/openvswitch/datapath.c68
-rw-r--r--net/openvswitch/datapath.h2
-rw-r--r--net/openvswitch/flow.c145
-rw-r--r--net/openvswitch/flow.h14
-rw-r--r--net/openvswitch/flow_netlink.c144
-rw-r--r--net/openvswitch/meter.c15
-rw-r--r--net/openvswitch/vport-internal_dev.c5
-rw-r--r--net/openvswitch/vport-netdev.c6
-rw-r--r--net/openvswitch/vport.c2
-rw-r--r--net/openvswitch/vport.h4
12 files changed, 477 insertions, 127 deletions
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 076774034bb9..ca3ebfdb3023 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -373,6 +373,7 @@ static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
update_ip_l4_checksum(skb, nh, *addr, new_addr);
csum_replace4(&nh->check, *addr, new_addr);
skb_clear_hash(skb);
+ ovs_ct_clear(skb, NULL);
*addr = new_addr;
}
@@ -420,15 +421,47 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto,
update_ipv6_checksum(skb, l4_proto, addr, new_addr);
skb_clear_hash(skb);
+ ovs_ct_clear(skb, NULL);
memcpy(addr, new_addr, sizeof(__be32[4]));
}
-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask)
+static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask)
{
+ u8 old_ipv6_tclass = ipv6_get_dsfield(nh);
+
+ ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask);
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12),
+ (__force __wsum)(ipv6_tclass << 12));
+
+ ipv6_change_dsfield(nh, ~mask, ipv6_tclass);
+}
+
+static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask)
+{
+ u32 ofl;
+
+ ofl = nh->flow_lbl[0] << 16 | nh->flow_lbl[1] << 8 | nh->flow_lbl[2];
+ fl = OVS_MASKED(ofl, fl, mask);
+
/* Bits 21-24 are always unmasked, so this retains their values. */
- OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16));
- OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8));
- OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask);
+ nh->flow_lbl[0] = (u8)(fl >> 16);
+ nh->flow_lbl[1] = (u8)(fl >> 8);
+ nh->flow_lbl[2] = (u8)fl;
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl));
+}
+
+static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask)
+{
+ new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask);
+
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8),
+ (__force __wsum)(new_ttl << 8));
+ nh->hop_limit = new_ttl;
}
static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl,
@@ -546,18 +579,17 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key,
}
}
if (mask->ipv6_tclass) {
- ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass);
+ set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass);
flow_key->ip.tos = ipv6_get_dsfield(nh);
}
if (mask->ipv6_label) {
- set_ipv6_fl(nh, ntohl(key->ipv6_label),
+ set_ipv6_fl(skb, nh, ntohl(key->ipv6_label),
ntohl(mask->ipv6_label));
flow_key->ipv6.label =
*(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
}
if (mask->ipv6_hlimit) {
- OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit,
- mask->ipv6_hlimit);
+ set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit);
flow_key->ip.ttl = nh->hop_limit;
}
return 0;
@@ -630,6 +662,7 @@ static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key,
static void set_tp_port(struct sk_buff *skb, __be16 *port,
__be16 new_port, __sum16 *check)
{
+ ovs_ct_clear(skb, NULL);
inet_proto_csum_replace2(check, skb, *port, new_port, false);
*port = new_port;
}
@@ -669,6 +702,7 @@ static int set_udp(struct sk_buff *skb, struct sw_flow_key *flow_key,
uh->dest = dst;
flow_key->tp.src = src;
flow_key->tp.dst = dst;
+ ovs_ct_clear(skb, NULL);
}
skb_clear_hash(skb);
@@ -731,6 +765,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
sh->checksum = old_csum ^ old_correct_csum ^ new_csum;
skb_clear_hash(skb);
+ ovs_ct_clear(skb, NULL);
+
flow_key->tp.src = sh->source;
flow_key->tp.dst = sh->dest;
@@ -997,7 +1033,7 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
actions = nla_next(sample_arg, &rem);
if ((arg->probability != U32_MAX) &&
- (!arg->probability || prandom_u32() > arg->probability)) {
+ (!arg->probability || get_random_u32() > arg->probability)) {
if (last)
consume_skb(skb);
return 0;
@@ -1021,7 +1057,7 @@ static int clone(struct datapath *dp, struct sk_buff *skb,
int rem = nla_len(attr);
bool dont_clone_flow_key;
- /* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+ /* The first action is always 'OVS_CLONE_ATTR_EXEC'. */
clone_arg = nla_data(attr);
dont_clone_flow_key = nla_get_u32(clone_arg);
actions = nla_next(clone_arg, &rem);
@@ -1509,8 +1545,8 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
pr_warn("%s: deferred action limit reached, drop sample action\n",
ovs_dp_name(dp));
} else { /* Recirc action */
- pr_warn("%s: deferred action limit reached, drop recirc action\n",
- ovs_dp_name(dp));
+ pr_warn("%s: deferred action limit reached, drop recirc action (recirc_id=%#x)\n",
+ ovs_dp_name(dp), recirc_id);
}
}
}
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index c07afff57dd3..c7b10234cf7c 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -734,6 +734,57 @@ static bool skb_nfct_cached(struct net *net,
}
#if IS_ENABLED(CONFIG_NF_NAT)
+static void ovs_nat_update_key(struct sw_flow_key *key,
+ const struct sk_buff *skb,
+ enum nf_nat_manip_type maniptype)
+{
+ if (maniptype == NF_NAT_MANIP_SRC) {
+ __be16 src;
+
+ key->ct_state |= OVS_CS_F_SRC_NAT;
+ if (key->eth.type == htons(ETH_P_IP))
+ key->ipv4.addr.src = ip_hdr(skb)->saddr;
+ else if (key->eth.type == htons(ETH_P_IPV6))
+ memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
+ sizeof(key->ipv6.addr.src));
+ else
+ return;
+
+ if (key->ip.proto == IPPROTO_UDP)
+ src = udp_hdr(skb)->source;
+ else if (key->ip.proto == IPPROTO_TCP)
+ src = tcp_hdr(skb)->source;
+ else if (key->ip.proto == IPPROTO_SCTP)
+ src = sctp_hdr(skb)->source;
+ else
+ return;
+
+ key->tp.src = src;
+ } else {
+ __be16 dst;
+
+ key->ct_state |= OVS_CS_F_DST_NAT;
+ if (key->eth.type == htons(ETH_P_IP))
+ key->ipv4.addr.dst = ip_hdr(skb)->daddr;
+ else if (key->eth.type == htons(ETH_P_IPV6))
+ memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
+ sizeof(key->ipv6.addr.dst));
+ else
+ return;
+
+ if (key->ip.proto == IPPROTO_UDP)
+ dst = udp_hdr(skb)->dest;
+ else if (key->ip.proto == IPPROTO_TCP)
+ dst = tcp_hdr(skb)->dest;
+ else if (key->ip.proto == IPPROTO_SCTP)
+ dst = sctp_hdr(skb)->dest;
+ else
+ return;
+
+ key->tp.dst = dst;
+ }
+}
+
/* Modelled after nf_nat_ipv[46]_fn().
* range is only used for new, uninitialized NAT state.
* Returns either NF_ACCEPT or NF_DROP.
@@ -741,7 +792,7 @@ static bool skb_nfct_cached(struct net *net,
static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
enum ip_conntrack_info ctinfo,
const struct nf_nat_range2 *range,
- enum nf_nat_manip_type maniptype)
+ enum nf_nat_manip_type maniptype, struct sw_flow_key *key)
{
int hooknum, nh_off, err = NF_ACCEPT;
@@ -813,58 +864,11 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
push:
skb_push_rcsum(skb, nh_off);
- return err;
-}
-
-static void ovs_nat_update_key(struct sw_flow_key *key,
- const struct sk_buff *skb,
- enum nf_nat_manip_type maniptype)
-{
- if (maniptype == NF_NAT_MANIP_SRC) {
- __be16 src;
-
- key->ct_state |= OVS_CS_F_SRC_NAT;
- if (key->eth.type == htons(ETH_P_IP))
- key->ipv4.addr.src = ip_hdr(skb)->saddr;
- else if (key->eth.type == htons(ETH_P_IPV6))
- memcpy(&key->ipv6.addr.src, &ipv6_hdr(skb)->saddr,
- sizeof(key->ipv6.addr.src));
- else
- return;
-
- if (key->ip.proto == IPPROTO_UDP)
- src = udp_hdr(skb)->source;
- else if (key->ip.proto == IPPROTO_TCP)
- src = tcp_hdr(skb)->source;
- else if (key->ip.proto == IPPROTO_SCTP)
- src = sctp_hdr(skb)->source;
- else
- return;
-
- key->tp.src = src;
- } else {
- __be16 dst;
-
- key->ct_state |= OVS_CS_F_DST_NAT;
- if (key->eth.type == htons(ETH_P_IP))
- key->ipv4.addr.dst = ip_hdr(skb)->daddr;
- else if (key->eth.type == htons(ETH_P_IPV6))
- memcpy(&key->ipv6.addr.dst, &ipv6_hdr(skb)->daddr,
- sizeof(key->ipv6.addr.dst));
- else
- return;
-
- if (key->ip.proto == IPPROTO_UDP)
- dst = udp_hdr(skb)->dest;
- else if (key->ip.proto == IPPROTO_TCP)
- dst = tcp_hdr(skb)->dest;
- else if (key->ip.proto == IPPROTO_SCTP)
- dst = sctp_hdr(skb)->dest;
- else
- return;
+ /* Update the flow key if NAT successful. */
+ if (err == NF_ACCEPT)
+ ovs_nat_update_key(key, skb, maniptype);
- key->tp.dst = dst;
- }
+ return err;
}
/* Returns NF_DROP if the packet should be dropped, NF_ACCEPT otherwise. */
@@ -906,7 +910,7 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
} else {
return NF_ACCEPT; /* Connection is not NATed. */
}
- err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype);
+ err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype, key);
if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) {
if (ct->status & IPS_SRC_NAT) {
@@ -916,17 +920,13 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
maniptype = NF_NAT_MANIP_SRC;
err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range,
- maniptype);
+ maniptype, key);
} else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) {
err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL,
- NF_NAT_MANIP_SRC);
+ NF_NAT_MANIP_SRC, key);
}
}
- /* Mark NAT done if successful and update the flow key. */
- if (err == NF_ACCEPT)
- ovs_nat_update_key(key, skb, maniptype);
-
return err;
}
#else /* !CONFIG_NF_NAT */
@@ -1015,7 +1015,8 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
* connections which we will commit, we may need to attach
* the helper here.
*/
- if (info->commit && info->helper && !nfct_help(ct)) {
+ if (!nf_ct_is_confirmed(ct) && info->commit &&
+ info->helper && !nfct_help(ct)) {
int err = __nf_ct_try_assign_helper(ct, info->ct,
GFP_ATOMIC);
if (err)
@@ -1342,7 +1343,9 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key)
nf_ct_put(ct);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
- ovs_ct_fill_key(skb, key, false);
+
+ if (key)
+ ovs_ct_fill_key(skb, key, false);
return 0;
}
@@ -1980,7 +1983,8 @@ static int ovs_ct_limit_set_zone_limit(struct nlattr *nla_zone_limit,
} else {
struct ovs_ct_limit *ct_limit;
- ct_limit = kmalloc(sizeof(*ct_limit), GFP_KERNEL);
+ ct_limit = kmalloc(sizeof(*ct_limit),
+ GFP_KERNEL_ACCOUNT);
if (!ct_limit)
return -ENOMEM;
@@ -2250,14 +2254,16 @@ exit_err:
static const struct genl_small_ops ct_limit_genl_ops[] = {
{ .cmd = OVS_CT_LIMIT_CMD_SET,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
- * privilege. */
+ .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+ * privilege.
+ */
.doit = ovs_ct_limit_cmd_set,
},
{ .cmd = OVS_CT_LIMIT_CMD_DEL,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
- * privilege. */
+ .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+ * privilege.
+ */
.doit = ovs_ct_limit_cmd_del,
},
{ .cmd = OVS_CT_LIMIT_CMD_GET,
@@ -2281,6 +2287,7 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = ct_limit_genl_ops,
.n_small_ops = ARRAY_SIZE(ct_limit_genl_ops),
+ .resv_start_op = OVS_CT_LIMIT_CMD_GET + 1,
.mcgrps = &ovs_ct_limit_multicast_group,
.n_mcgrps = 1,
.module = THIS_MODULE,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 67ad08320886..8b84869eb2ac 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -37,6 +37,7 @@
#include <net/genetlink.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
+#include <net/pkt_cls.h>
#include "datapath.h"
#include "flow.h"
@@ -251,10 +252,17 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
upcall.mru = OVS_CB(skb)->mru;
error = ovs_dp_upcall(dp, skb, key, &upcall, 0);
- if (unlikely(error))
- kfree_skb(skb);
- else
+ switch (error) {
+ case 0:
+ case -EAGAIN:
+ case -ERESTARTSYS:
+ case -EINTR:
consume_skb(skb);
+ break;
+ default:
+ kfree_skb(skb);
+ break;
+ }
stats_counter = &stats->n_missed;
goto out;
}
@@ -550,8 +558,9 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
out:
if (err)
skb_tx_error(skb);
- kfree_skb(user_skb);
- kfree_skb(nskb);
+ consume_skb(user_skb);
+ consume_skb(nskb);
+
return err;
}
@@ -683,6 +692,7 @@ static struct genl_family dp_packet_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = dp_packet_genl_ops,
.n_small_ops = ARRAY_SIZE(dp_packet_genl_ops),
+ .resv_start_op = OVS_PACKET_CMD_EXECUTE + 1,
.module = THIS_MODULE,
};
@@ -1500,6 +1510,7 @@ static struct genl_family dp_flow_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = dp_flow_genl_ops,
.n_small_ops = ARRAY_SIZE(dp_flow_genl_ops),
+ .resv_start_op = OVS_FLOW_CMD_SET + 1,
.mcgrps = &ovs_dp_flow_multicast_group,
.n_mcgrps = 1,
.module = THIS_MODULE,
@@ -1514,6 +1525,7 @@ static size_t ovs_dp_cmd_msg_size(void)
msgsize += nla_total_size_64bit(sizeof(struct ovs_dp_megaflow_stats));
msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_USER_FEATURES */
msgsize += nla_total_size(sizeof(u32)); /* OVS_DP_ATTR_MASKS_CACHE_SIZE */
+ msgsize += nla_total_size(sizeof(u32) * nr_cpu_ids); /* OVS_DP_ATTR_PER_CPU_PIDS */
return msgsize;
}
@@ -1525,7 +1537,8 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
struct ovs_header *ovs_header;
struct ovs_dp_stats dp_stats;
struct ovs_dp_megaflow_stats dp_megaflow_stats;
- int err;
+ struct dp_nlsk_pids *pids = ovsl_dereference(dp->upcall_portids);
+ int err, pids_len;
ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family,
flags, cmd);
@@ -1555,6 +1568,12 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
ovs_flow_tbl_masks_cache_size(&dp->table)))
goto nla_put_failure;
+ if (dp->user_features & OVS_DP_F_DISPATCH_UPCALL_PER_CPU && pids) {
+ pids_len = min(pids->n_pids, nr_cpu_ids) * sizeof(u32);
+ if (nla_put(skb, OVS_DP_ATTR_PER_CPU_PIDS, pids_len, &pids->pids))
+ goto nla_put_failure;
+ }
+
genlmsg_end(skb, ovs_header);
return 0;
@@ -1597,12 +1616,11 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb,
if (IS_ERR(dp))
return;
- WARN(dp->user_features, "Dropping previously announced user features\n");
+ pr_warn("%s: Dropping previously announced user features\n",
+ ovs_dp_name(dp));
dp->user_features = 0;
}
-DEFINE_STATIC_KEY_FALSE(tc_recirc_sharing_support);
-
static int ovs_dp_set_upcall_portids(struct datapath *dp,
const struct nlattr *ids)
{
@@ -1657,7 +1675,7 @@ u32 ovs_dp_get_upcall_portid(const struct datapath *dp, uint32_t cpu_id)
static int ovs_dp_change(struct datapath *dp, struct nlattr *a[])
{
- u32 user_features = 0;
+ u32 user_features = 0, old_features = dp->user_features;
int err;
if (a[OVS_DP_ATTR_USER_FEATURES]) {
@@ -1696,10 +1714,12 @@ static int ovs_dp_change(struct datapath *dp, struct nlattr *a[])
return err;
}
- if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING)
- static_branch_enable(&tc_recirc_sharing_support);
- else
- static_branch_disable(&tc_recirc_sharing_support);
+ if ((dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) &&
+ !(old_features & OVS_DP_F_TC_RECIRC_SHARING))
+ tc_skb_ext_tc_enable();
+ else if (!(dp->user_features & OVS_DP_F_TC_RECIRC_SHARING) &&
+ (old_features & OVS_DP_F_TC_RECIRC_SHARING))
+ tc_skb_ext_tc_disable();
return 0;
}
@@ -1778,6 +1798,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
parms.dp = dp;
parms.port_no = OVSP_LOCAL;
parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
+ parms.desired_ifindex = a[OVS_DP_ATTR_IFINDEX]
+ ? nla_get_u32(a[OVS_DP_ATTR_IFINDEX]) : 0;
/* So far only local changes have been made, now need the lock. */
ovs_lock();
@@ -1801,7 +1823,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
ovs_dp_reset_user_features(skb, info);
}
- goto err_unlock_and_destroy_meters;
+ goto err_destroy_portids;
}
err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1816,6 +1838,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
ovs_notify(&dp_datapath_genl_family, reply, info);
return 0;
+err_destroy_portids:
+ kfree(rcu_dereference_raw(dp->upcall_portids));
err_unlock_and_destroy_meters:
ovs_unlock();
ovs_meters_exit(dp);
@@ -1839,6 +1863,9 @@ static void __dp_destroy(struct datapath *dp)
struct flow_table *table = &dp->table;
int i;
+ if (dp->user_features & OVS_DP_F_TC_RECIRC_SHARING)
+ tc_skb_ext_tc_disable();
+
for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
struct vport *vport;
struct hlist_node *n;
@@ -1992,6 +2019,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
[OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 },
[OVS_DP_ATTR_MASKS_CACHE_SIZE] = NLA_POLICY_RANGE(NLA_U32, 0,
PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)),
+ [OVS_DP_ATTR_IFINDEX] = {.type = NLA_U32 },
};
static const struct genl_small_ops dp_datapath_genl_ops[] = {
@@ -2028,6 +2056,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = dp_datapath_genl_ops,
.n_small_ops = ARRAY_SIZE(dp_datapath_genl_ops),
+ .resv_start_op = OVS_DP_CMD_SET + 1,
.mcgrps = &ovs_dp_datapath_multicast_group,
.n_mcgrps = 1,
.module = THIS_MODULE,
@@ -2195,7 +2224,10 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
!a[OVS_VPORT_ATTR_UPCALL_PID])
return -EINVAL;
- if (a[OVS_VPORT_ATTR_IFINDEX])
+
+ parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]);
+
+ if (a[OVS_VPORT_ATTR_IFINDEX] && parms.type != OVS_VPORT_TYPE_INTERNAL)
return -EOPNOTSUPP;
port_no = a[OVS_VPORT_ATTR_PORT_NO]
@@ -2232,11 +2264,12 @@ restart:
}
parms.name = nla_data(a[OVS_VPORT_ATTR_NAME]);
- parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]);
parms.options = a[OVS_VPORT_ATTR_OPTIONS];
parms.dp = dp;
parms.port_no = port_no;
parms.upcall_portids = a[OVS_VPORT_ATTR_UPCALL_PID];
+ parms.desired_ifindex = a[OVS_VPORT_ATTR_IFINDEX]
+ ? nla_get_u32(a[OVS_VPORT_ATTR_IFINDEX]) : 0;
vport = new_vport(&parms);
err = PTR_ERR(vport);
@@ -2511,6 +2544,7 @@ struct genl_family dp_vport_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = dp_vport_genl_ops,
.n_small_ops = ARRAY_SIZE(dp_vport_genl_ops),
+ .resv_start_op = OVS_VPORT_CMD_SET + 1,
.mcgrps = &ovs_dp_vport_multicast_group,
.n_mcgrps = 1,
.module = THIS_MODULE,
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index fcfe6cb46441..0cd29971a907 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -253,8 +253,6 @@ static inline struct datapath *get_dp(struct net *net, int dp_ifindex)
extern struct notifier_block ovs_dp_device_notifier;
extern struct genl_family dp_vport_genl_family;
-DECLARE_STATIC_KEY_FALSE(tc_recirc_sharing_support);
-
void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key);
void ovs_dp_detach_port(struct vport *);
int ovs_dp_upcall(struct datapath *, struct sk_buff *,
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 02096f2ec678..e20d1a973417 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -34,6 +34,7 @@
#include <net/mpls.h>
#include <net/ndisc.h>
#include <net/nsh.h>
+#include <net/pkt_cls.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include "conntrack.h"
@@ -240,6 +241,144 @@ static bool icmphdr_ok(struct sk_buff *skb)
sizeof(struct icmphdr));
}
+/**
+ * get_ipv6_ext_hdrs() - Parses packet and sets IPv6 extension header flags.
+ *
+ * @skb: buffer where extension header data starts in packet
+ * @nh: ipv6 header
+ * @ext_hdrs: flags are stored here
+ *
+ * OFPIEH12_UNREP is set if more than one of a given IPv6 extension header
+ * is unexpectedly encountered. (Two destination options headers may be
+ * expected and would not cause this bit to be set.)
+ *
+ * OFPIEH12_UNSEQ is set if IPv6 extension headers were not in the order
+ * preferred (but not required) by RFC 2460:
+ *
+ * When more than one extension header is used in the same packet, it is
+ * recommended that those headers appear in the following order:
+ * IPv6 header
+ * Hop-by-Hop Options header
+ * Destination Options header
+ * Routing header
+ * Fragment header
+ * Authentication header
+ * Encapsulating Security Payload header
+ * Destination Options header
+ * upper-layer header
+ */
+static void get_ipv6_ext_hdrs(struct sk_buff *skb, struct ipv6hdr *nh,
+ u16 *ext_hdrs)
+{
+ u8 next_type = nh->nexthdr;
+ unsigned int start = skb_network_offset(skb) + sizeof(struct ipv6hdr);
+ int dest_options_header_count = 0;
+
+ *ext_hdrs = 0;
+
+ while (ipv6_ext_hdr(next_type)) {
+ struct ipv6_opt_hdr _hdr, *hp;
+
+ switch (next_type) {
+ case IPPROTO_NONE:
+ *ext_hdrs |= OFPIEH12_NONEXT;
+ /* stop parsing */
+ return;
+
+ case IPPROTO_ESP:
+ if (*ext_hdrs & OFPIEH12_ESP)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs & ~(OFPIEH12_HOP | OFPIEH12_DEST |
+ OFPIEH12_ROUTER | IPPROTO_FRAGMENT |
+ OFPIEH12_AUTH | OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_ESP;
+ break;
+
+ case IPPROTO_AH:
+ if (*ext_hdrs & OFPIEH12_AUTH)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs &
+ ~(OFPIEH12_HOP | OFPIEH12_DEST | OFPIEH12_ROUTER |
+ IPPROTO_FRAGMENT | OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_AUTH;
+ break;
+
+ case IPPROTO_DSTOPTS:
+ if (dest_options_header_count == 0) {
+ if (*ext_hdrs &
+ ~(OFPIEH12_HOP | OFPIEH12_UNREP))
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ *ext_hdrs |= OFPIEH12_DEST;
+ } else if (dest_options_header_count == 1) {
+ if (*ext_hdrs &
+ ~(OFPIEH12_HOP | OFPIEH12_DEST |
+ OFPIEH12_ROUTER | OFPIEH12_FRAG |
+ OFPIEH12_AUTH | OFPIEH12_ESP |
+ OFPIEH12_UNREP)) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ } else {
+ *ext_hdrs |= OFPIEH12_UNREP;
+ }
+ dest_options_header_count++;
+ break;
+
+ case IPPROTO_FRAGMENT:
+ if (*ext_hdrs & OFPIEH12_FRAG)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs & ~(OFPIEH12_HOP |
+ OFPIEH12_DEST |
+ OFPIEH12_ROUTER |
+ OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_FRAG;
+ break;
+
+ case IPPROTO_ROUTING:
+ if (*ext_hdrs & OFPIEH12_ROUTER)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ if ((*ext_hdrs & ~(OFPIEH12_HOP |
+ OFPIEH12_DEST |
+ OFPIEH12_UNREP)) ||
+ dest_options_header_count >= 2) {
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ }
+ *ext_hdrs |= OFPIEH12_ROUTER;
+ break;
+
+ case IPPROTO_HOPOPTS:
+ if (*ext_hdrs & OFPIEH12_HOP)
+ *ext_hdrs |= OFPIEH12_UNREP;
+ /* OFPIEH12_HOP is set to 1 if a hop-by-hop IPv6
+ * extension header is present as the first
+ * extension header in the packet.
+ */
+ if (*ext_hdrs == 0)
+ *ext_hdrs |= OFPIEH12_HOP;
+ else
+ *ext_hdrs |= OFPIEH12_UNSEQ;
+ break;
+
+ default:
+ return;
+ }
+
+ hp = skb_header_pointer(skb, start, sizeof(_hdr), &_hdr);
+ if (!hp)
+ break;
+ next_type = hp->nexthdr;
+ start += ipv6_optlen(hp);
+ }
+}
+
static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
{
unsigned short frag_off;
@@ -255,6 +394,8 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
nh = ipv6_hdr(skb);
+ get_ipv6_ext_hdrs(skb, nh, &key->ipv6.exthdrs);
+
key->ip.proto = NEXTHDR_NONE;
key->ip.tos = ipv6_get_dsfield(nh);
key->ip.ttl = nh->hop_limit;
@@ -266,7 +407,7 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key)
if (flags & IP6_FH_F_FRAG) {
if (frag_off) {
key->ip.frag = OVS_FRAG_TYPE_LATER;
- key->ip.proto = nexthdr;
+ key->ip.proto = NEXTHDR_FRAGMENT;
return 0;
}
key->ip.frag = OVS_FRAG_TYPE_FIRST;
@@ -895,7 +1036,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info,
key->mac_proto = res;
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
- if (static_branch_unlikely(&tc_recirc_sharing_support)) {
+ if (tc_skb_ext_tc_enabled()) {
tc_ext = skb_ext_find(skb, TC_SKB_EXT);
key->recirc_id = tc_ext ? tc_ext->chain : 0;
OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 758a8c77f736..073ab73ffeaa 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -32,6 +32,19 @@ enum sw_flow_mac_proto {
#define SW_FLOW_KEY_INVALID 0x80
#define MPLS_LABEL_DEPTH 3
+/* Bit definitions for IPv6 Extension Header pseudo-field. */
+enum ofp12_ipv6exthdr_flags {
+ OFPIEH12_NONEXT = 1 << 0, /* "No next header" encountered. */
+ OFPIEH12_ESP = 1 << 1, /* Encrypted Sec Payload header present. */
+ OFPIEH12_AUTH = 1 << 2, /* Authentication header present. */
+ OFPIEH12_DEST = 1 << 3, /* 1 or 2 dest headers present. */
+ OFPIEH12_FRAG = 1 << 4, /* Fragment header present. */
+ OFPIEH12_ROUTER = 1 << 5, /* Router header present. */
+ OFPIEH12_HOP = 1 << 6, /* Hop-by-hop header present. */
+ OFPIEH12_UNREP = 1 << 7, /* Unexpected repeats encountered. */
+ OFPIEH12_UNSEQ = 1 << 8 /* Unexpected sequencing encountered. */
+};
+
/* Store options at the end of the array if they are less than the
* maximum size. This allows us to get the benefits of variable length
* matching for small options.
@@ -121,6 +134,7 @@ struct sw_flow_key {
struct in6_addr dst; /* IPv6 destination address. */
} addr;
__be32 label; /* IPv6 flow label. */
+ u16 exthdrs; /* IPv6 extension header flags */
union {
struct {
struct in6_addr src;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index fd1f809e9bc1..4a07ab094a84 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -346,7 +346,7 @@ size_t ovs_key_attr_size(void)
/* Whenever adding new OVS_KEY_ FIELDS, we should consider
* updating this function.
*/
- BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 29);
+ BUILD_BUG_ON(OVS_KEY_ATTR_MAX != 32);
return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */
+ nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */
@@ -369,7 +369,8 @@ size_t ovs_key_attr_size(void)
+ nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */
+ nla_total_size(40) /* OVS_KEY_ATTR_IPV6 */
+ nla_total_size(2) /* OVS_KEY_ATTR_ICMPV6 */
- + nla_total_size(28); /* OVS_KEY_ATTR_ND */
+ + nla_total_size(28) /* OVS_KEY_ATTR_ND */
+ + nla_total_size(2); /* OVS_KEY_ATTR_IPV6_EXTHDRS */
}
static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
@@ -437,6 +438,8 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
[OVS_KEY_ATTR_NSH] = { .len = OVS_ATTR_NESTED,
.next = ovs_nsh_key_attr_lens, },
+ [OVS_KEY_ATTR_IPV6_EXTHDRS] = {
+ .len = sizeof(struct ovs_key_ipv6_exthdrs) },
};
static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
@@ -479,7 +482,14 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
return -EINVAL;
}
- if (attrs & (1 << type)) {
+ if (type == OVS_KEY_ATTR_PACKET_TYPE ||
+ type == OVS_KEY_ATTR_ND_EXTENSIONS ||
+ type == OVS_KEY_ATTR_TUNNEL_INFO) {
+ OVS_NLERR(log, "Key type %d is not supported", type);
+ return -EINVAL;
+ }
+
+ if (attrs & (1ULL << type)) {
OVS_NLERR(log, "Duplicate key (type %d).", type);
return -EINVAL;
}
@@ -492,7 +502,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr,
}
if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) {
- attrs |= 1 << type;
+ attrs |= 1ULL << type;
a[type] = nla;
}
}
@@ -1597,6 +1607,17 @@ static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
}
+ if (attrs & (1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS)) {
+ const struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
+
+ ipv6_exthdrs_key = nla_data(a[OVS_KEY_ATTR_IPV6_EXTHDRS]);
+
+ SW_FLOW_KEY_PUT(match, ipv6.exthdrs,
+ ipv6_exthdrs_key->hdrs, is_mask);
+
+ attrs &= ~(1ULL << OVS_KEY_ATTR_IPV6_EXTHDRS);
+ }
+
if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
const struct ovs_key_arp *arp_key;
@@ -2099,6 +2120,7 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
ipv4_key->ipv4_frag = output->ip.frag;
} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
struct ovs_key_ipv6 *ipv6_key;
+ struct ovs_key_ipv6_exthdrs *ipv6_exthdrs_key;
nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
if (!nla)
@@ -2113,6 +2135,13 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
ipv6_key->ipv6_tclass = output->ip.tos;
ipv6_key->ipv6_hlimit = output->ip.ttl;
ipv6_key->ipv6_frag = output->ip.frag;
+
+ nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6_EXTHDRS,
+ sizeof(*ipv6_exthdrs_key));
+ if (!nla)
+ goto nla_put_failure;
+ ipv6_exthdrs_key = nla_data(nla);
+ ipv6_exthdrs_key->hdrs = output->ipv6.exthdrs;
} else if (swkey->eth.type == htons(ETH_P_NSH)) {
if (nsh_key_to_nlattr(&output->nsh, is_mask, skb))
goto nla_put_failure;
@@ -2201,8 +2230,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
icmpv6_key->icmpv6_type = ntohs(output->tp.src);
icmpv6_key->icmpv6_code = ntohs(output->tp.dst);
- if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
- icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
+ if (swkey->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+ swkey->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
struct ovs_key_nd *nd_key;
nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
@@ -2288,6 +2317,62 @@ static struct sw_flow_actions *nla_alloc_flow_actions(int size)
return sfa;
}
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len);
+
+static void ovs_nla_free_check_pkt_len_action(const struct nlattr *action)
+{
+ const struct nlattr *a;
+ int rem;
+
+ nla_for_each_nested(a, action, rem) {
+ switch (nla_type(a)) {
+ case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL:
+ case OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER:
+ ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+ break;
+ }
+ }
+}
+
+static void ovs_nla_free_clone_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+ int rem = nla_len(action);
+
+ switch (nla_type(a)) {
+ case OVS_CLONE_ATTR_EXEC:
+ /* The real list of actions follows this attribute. */
+ a = nla_next(a, &rem);
+ ovs_nla_free_nested_actions(a, rem);
+ break;
+ }
+}
+
+static void ovs_nla_free_dec_ttl_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+
+ switch (nla_type(a)) {
+ case OVS_DEC_TTL_ATTR_ACTION:
+ ovs_nla_free_nested_actions(nla_data(a), nla_len(a));
+ break;
+ }
+}
+
+static void ovs_nla_free_sample_action(const struct nlattr *action)
+{
+ const struct nlattr *a = nla_data(action);
+ int rem = nla_len(action);
+
+ switch (nla_type(a)) {
+ case OVS_SAMPLE_ATTR_ARG:
+ /* The real list of actions follows this attribute. */
+ a = nla_next(a, &rem);
+ ovs_nla_free_nested_actions(a, rem);
+ break;
+ }
+}
+
static void ovs_nla_free_set_action(const struct nlattr *a)
{
const struct nlattr *ovs_key = nla_data(a);
@@ -2301,25 +2386,54 @@ static void ovs_nla_free_set_action(const struct nlattr *a)
}
}
-void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+static void ovs_nla_free_nested_actions(const struct nlattr *actions, int len)
{
const struct nlattr *a;
int rem;
- if (!sf_acts)
+ /* Whenever new actions are added, the need to update this
+ * function should be considered.
+ */
+ BUILD_BUG_ON(OVS_ACTION_ATTR_MAX != 23);
+
+ if (!actions)
return;
- nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
+ nla_for_each_attr(a, actions, len, rem) {
switch (nla_type(a)) {
- case OVS_ACTION_ATTR_SET:
- ovs_nla_free_set_action(a);
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ ovs_nla_free_check_pkt_len_action(a);
break;
+
+ case OVS_ACTION_ATTR_CLONE:
+ ovs_nla_free_clone_action(a);
+ break;
+
case OVS_ACTION_ATTR_CT:
ovs_ct_free_action(a);
break;
+
+ case OVS_ACTION_ATTR_DEC_TTL:
+ ovs_nla_free_dec_ttl_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_SAMPLE:
+ ovs_nla_free_sample_action(a);
+ break;
+
+ case OVS_ACTION_ATTR_SET:
+ ovs_nla_free_set_action(a);
+ break;
}
}
+}
+
+void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
+{
+ if (!sf_acts)
+ return;
+ ovs_nla_free_nested_actions(sf_acts->actions, sf_acts->actions_len);
kfree(sf_acts);
}
@@ -2351,7 +2465,7 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
- if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
+ if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) {
OVS_NLERR(log, "Flow action size exceeds max %u",
MAX_ACTIONS_BUFSIZE);
return ERR_PTR(-EMSGSIZE);
@@ -3190,7 +3304,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
/* Disallow subsequent L2.5+ set actions and mpls_pop
* actions once the last MPLS label in the packet is
- * is popped as there is no check here to ensure that
+ * popped as there is no check here to ensure that
* the new eth type is valid and thus set actions could
* write off the end of the packet or otherwise corrupt
* it.
@@ -3429,7 +3543,9 @@ static int clone_action_to_attr(const struct nlattr *attr,
if (!start)
return -EMSGSIZE;
- err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+ /* Skipping the OVS_CLONE_ATTR_EXEC that is always the first attribute. */
+ attr = nla_next(nla_data(attr), &rem);
+ err = ovs_nla_put_actions(attr, rem, skb);
if (err)
nla_nest_cancel(skb, start);
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 04a060ac7fdf..6e38f68f88c2 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -343,7 +343,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a)
return ERR_PTR(-EINVAL);
/* Allocate and set up the meter before locking anything. */
- meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL);
+ meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL_ACCOUNT);
if (!meter)
return ERR_PTR(-ENOMEM);
@@ -687,9 +687,9 @@ static const struct genl_small_ops dp_meter_genl_ops[] = {
},
{ .cmd = OVS_METER_CMD_SET,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
- * privilege.
- */
+ .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+ * privilege.
+ */
.doit = ovs_meter_cmd_set,
},
{ .cmd = OVS_METER_CMD_GET,
@@ -699,9 +699,9 @@ static const struct genl_small_ops dp_meter_genl_ops[] = {
},
{ .cmd = OVS_METER_CMD_DEL,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
- .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
- * privilege.
- */
+ .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN
+ * privilege.
+ */
.doit = ovs_meter_cmd_del
},
};
@@ -720,6 +720,7 @@ struct genl_family dp_meter_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = dp_meter_genl_ops,
.n_small_ops = ARRAY_SIZE(dp_meter_genl_ops),
+ .resv_start_op = OVS_METER_CMD_GET + 1,
.mcgrps = &ovs_meter_multicast_group,
.n_mcgrps = 1,
.module = THIS_MODULE,
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 5b2ee9c1c00b..74c88a6baa43 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -65,7 +65,7 @@ static int internal_dev_stop(struct net_device *netdev)
static void internal_dev_getinfo(struct net_device *netdev,
struct ethtool_drvinfo *info)
{
- strlcpy(info->driver, "openvswitch", sizeof(info->driver));
+ strscpy(info->driver, "openvswitch", sizeof(info->driver));
}
static const struct ethtool_ops internal_dev_ethtool_ops = {
@@ -147,6 +147,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
}
dev_net_set(vport->dev, ovs_dp_get_net(vport->dp));
+ dev->ifindex = parms->desired_ifindex;
internal_dev = internal_dev_priv(vport->dev);
internal_dev->vport = vport;
@@ -189,7 +190,7 @@ static void internal_dev_destroy(struct vport *vport)
rtnl_unlock();
}
-static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
+static int internal_dev_recv(struct sk_buff *skb)
{
struct net_device *netdev = skb->dev;
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
index b498dac4e1e0..2f61d5bdce1a 100644
--- a/net/openvswitch/vport-netdev.c
+++ b/net/openvswitch/vport-netdev.c
@@ -115,7 +115,7 @@ error_master_upper_dev_unlink:
error_unlock:
rtnl_unlock();
error_put:
- dev_put_track(vport->dev, &vport->dev_tracker);
+ netdev_put(vport->dev, &vport->dev_tracker);
error_free_vport:
ovs_vport_free(vport);
return ERR_PTR(err);
@@ -137,7 +137,7 @@ static void vport_netdev_free(struct rcu_head *rcu)
{
struct vport *vport = container_of(rcu, struct vport, rcu);
- dev_put_track(vport->dev, &vport->dev_tracker);
+ netdev_put(vport->dev, &vport->dev_tracker);
ovs_vport_free(vport);
}
@@ -173,7 +173,7 @@ void ovs_netdev_tunnel_destroy(struct vport *vport)
*/
if (vport->dev->reg_state == NETREG_REGISTERED)
rtnl_delete_link(vport->dev);
- dev_put_track(vport->dev, &vport->dev_tracker);
+ netdev_put(vport->dev, &vport->dev_tracker);
vport->dev = NULL;
rtnl_unlock();
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index cf2ce5812489..82a74f998966 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -507,7 +507,7 @@ void ovs_vport_send(struct vport *vport, struct sk_buff *skb, u8 mac_proto)
}
skb->dev = vport->dev;
- skb->tstamp = 0;
+ skb_clear_tstamp(skb);
vport->ops->send(skb);
return;
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 9de5030d9801..6ff45e8a0868 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -90,12 +90,14 @@ struct vport {
* @type: New vport's type.
* @options: %OVS_VPORT_ATTR_OPTIONS attribute from Netlink message, %NULL if
* none was supplied.
+ * @desired_ifindex: New vport's ifindex.
* @dp: New vport's datapath.
* @port_no: New vport's port number.
*/
struct vport_parms {
const char *name;
enum ovs_vport_type type;
+ int desired_ifindex;
struct nlattr *options;
/* For ovs_vport_alloc(). */
@@ -130,7 +132,7 @@ struct vport_ops {
int (*set_options)(struct vport *, struct nlattr *);
int (*get_options)(const struct vport *, struct sk_buff *);
- netdev_tx_t (*send) (struct sk_buff *skb);
+ int (*send)(struct sk_buff *skb);
struct module *owner;
struct list_head list;
};
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.